verified-research
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data from the open web as part of its core functionality (research and fact-checking).
- Ingestion points: Data is ingested from the internet via the search, fetch, fetch_batch, research, and read_doc tools.
- Boundary markers: The instructions provide logical boundaries by directing the agent to distinguish between primary and secondary sources and to report citations with specific metadata (dates, URLs).
- Capability inventory: The skill utilizes tools for web search, document reading, and structured data extraction. It does not appear to possess tools for filesystem modification, shell access, or secret exfiltration.
- Sanitization: No programmatic sanitization is defined; the skill relies on the agent's analytical capabilities to verify and report on the ingested content.
Audit Metadata